Group Analysis
Johanna Mehler
2024-03-28
1 Differences in indicators between academic status groups
1.1 Data preparation
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors## here() starts at /Users/Jo/OneDrive/1_Hertie Studies/Thesis/Hertie-Thesis-Mehler## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2##
## Attaching package: 'rstatix'
##
## The following object is masked from 'package:stats':
##
## filter## Rows: 1019 Columns: 24
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (12): ResponseId, academic_status, educ_cat, gender, age_cat, polinteres...
## dbl (12): age, age10, polinterest, empathy_pc, exp_hate_speech, exp_hostile_...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.1.2 Indicators by Academic Status
p <- ggpairs(data, # Data frame
columns = indicators, # Columns
aes(color = academic_status, # Color by group (cat. variable)
alpha = 0.5),
upper = list(continuous = wrap("cor", size = 2.7)
))
p## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 664 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 664 rows containing missing values## Warning: Removed 664 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 664 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_boxplot()`).## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_bin()`).
1.3 Textlength and Academic Status
1.3.1 Mean, SD, T-Test
# logged textlength
data %>%
group_by(academic_status) %>%
get_summary_stats(text_length, type = "mean_sd")## # A tibble: 2 × 5
## academic_status variable n mean sd
## <chr> <fct> <dbl> <dbl> <dbl>
## 1 academic text_length 554 6.55 1.29
## 2 non-academic text_length 385 6.46 1.32##
## Welch Two Sample t-test
##
## data: text_length by academic_status
## t = 1.027, df = 813.87, p-value = 0.3047
## alternative hypothesis: true difference in means between group academic and group non-academic is not equal to 0
## 95 percent confidence interval:
## -0.08145726 0.26022895
## sample estimates:
## mean in group academic mean in group non-academic
## 6.551834 6.462449# statix version
stat.test <- data %>%
t_test(text_length ~ academic_status, detailed = TRUE) %>%
add_significance()
stat.test## # A tibble: 1 × 16
## estimate estimate1 estimate2 .y. group1 group2 n1 n2 statistic p
## <dbl> <dbl> <dbl> <chr> <chr> <chr> <int> <int> <dbl> <dbl>
## 1 0.0894 6.55 6.46 text_l… acade… non-a… 554 385 1.03 0.305
## # ℹ 6 more variables: df <dbl>, conf.low <dbl>, conf.high <dbl>, method <chr>,
## # alternative <chr>, p.signif <chr># Create a box-plot
bxp <- ggboxplot(
data, x = "academic_status", y = "text_length",
ylab = "Text Length", xlab = "Groups", add = "jitter"
)
# Add p-value and significance levels
stat.test <- stat.test %>% add_xy_position(x = "academic_status")
bxp +
stat_pvalue_manual(stat.test, tip.length = 0) +
labs(subtitle = get_test_label(stat.test, detailed = TRUE))
The T-Test shows no significance!
1.4 Readability and Academic Status
1.4.1 T-Test
# t-test
stat.test <- data %>%
t_test(readability_score ~ academic_status, detailed = TRUE) %>%
add_significance()
stat.test## # A tibble: 1 × 16
## estimate estimate1 estimate2 .y. group1 group2 n1 n2 statistic p
## <dbl> <dbl> <dbl> <chr> <chr> <chr> <int> <int> <dbl> <dbl>
## 1 0.971 11.9 11.0 read… acade… non-a… 554 385 2.65 0.00819
## # ℹ 6 more variables: df <dbl>, conf.low <dbl>, conf.high <dbl>, method <chr>,
## # alternative <chr>, p.signif <chr># Create a box-plot
bxp <- ggboxplot(
data, x = "academic_status", y = "readability_score",
ylab = "readability_score", xlab = "Groups", add = "jitter"
)
# Add p-value and significance levels
stat.test <- stat.test %>% add_xy_position(x = "academic_status")
bxp +
stat_pvalue_manual(stat.test, tip.length = 0) +
labs(subtitle = get_test_label(stat.test, detailed = TRUE))
1.5 Cluster Group and Academic Status
## Cell Contents
## |-------------------------|
## | Count |
## | Column Percent |
## |-------------------------|
##
## ===============================================
## data$academic_status
## data$cluster academic non-academic Total
## -----------------------------------------------
## A 167 109 276
## 30.1% 28.3%
## -----------------------------------------------
## B 188 116 304
## 33.9% 30.1%
## -----------------------------------------------
## C 87 87 174
## 15.7% 22.6%
## -----------------------------------------------
## D 112 73 185
## 20.2% 19.0%
## -----------------------------------------------
## Total 554 385 939
## 59% 41%
## ===============================================ggplot(data, aes(x = cluster, fill = academic_status)) +
geom_bar(position = "dodge") +
labs(title = "Number of Observations per Cluster, Grouped by Academic Status",
x = "Cluster",
y = "Number of Observations") +
theme_minimal()
1.6 Prediction of Political Orientation and Academic Status
1.6.1 T-Test
# t-test
stat.test <- data %>%
t_test(leftright_pred_score ~ academic_status, detailed = TRUE) %>%
add_significance()
stat.test## # A tibble: 1 × 16
## estimate estimate1 estimate2 .y. group1 group2 n1 n2 statistic p
## <dbl> <dbl> <dbl> <chr> <chr> <chr> <int> <int> <dbl> <dbl>
## 1 0.226 8.11 7.89 leftri… acade… non-a… 154 121 1.28 0.201
## # ℹ 6 more variables: df <dbl>, conf.low <dbl>, conf.high <dbl>, method <chr>,
## # alternative <chr>, p.signif <chr># Create a box-plot
bxp <- ggboxplot(
data, x = "academic_status", y = "leftright_pred_score",
ylab = "leftright pred score", xlab = "Groups", add = "jitter"
)
# Add p-value and significance levels
stat.test <- stat.test %>% add_xy_position(x = "academic_status")
bxp +
stat_pvalue_manual(stat.test, tip.length = 0) +
labs(subtitle = get_test_label(stat.test, detailed = TRUE))## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_boxplot()`).## Warning: Removed 664 rows containing missing values or values outside the scale range
## (`geom_point()`).
2 Differences in indicators between three edcucation levels
2.1 Indicators by Education Category
p <- ggpairs(data, # Data frame
columns = indicators, # Columns
aes(color = educ_cat, # Color by group (cat. variable)
alpha = 0.5),
upper = list(continuous = wrap("cor", size = 2.7)
))
p## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 664 rows containing missing values
## Warning in ggally_statistic(data = data, mapping = mapping, na.rm = na.rm, :
## Removed 664 rows containing missing values## Warning: Removed 664 rows containing missing values or values outside the scale range
## (`geom_point()`).
## Removed 664 rows containing missing values or values outside the scale range
## (`geom_point()`).## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_density()`).## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_boxplot()`).## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_bin()`).
2.2 Textlength and Education Cat
# Create the box plot
p <- ggplot(data, aes(x = educ_cat, y = text_length)) +
geom_point(position = position_jitter(width = 0.2), alpha = 0.5, color = "skyblue") +
geom_boxplot(outliers = FALSE) +
theme_minimal() +
labs(title = "Comparison of Text Length by Education",
x = "Academic Status",
y = "Text Length")
# Print the plot
print(p)
2.3 Readability and educ_cat
# Create the box plot
p <- ggplot(data, aes(x = educ_cat, y = readability_score)) +
geom_point(position = position_jitter(width = 0.2), alpha = 0.5, color = "skyblue") +
geom_boxplot(outliers = FALSE) +
theme_minimal() +
labs(title = "Comparison of Readability by Education",
x = "Academic Status",
y = "Readability Score")
# Print the plot
print(p)
2.4 Prediction of Political Orientation and educ_cat
# Create the box plot
p <- ggplot(data, aes(x = educ_cat, y = leftright_pred_score)) +
geom_point(position = position_jitter(width = 0.2), alpha = 0.5, color = "skyblue") +
geom_boxplot(outliers = FALSE) +
theme_minimal() +
labs(title = "Comparison of Prediction of Political Orientation by educ_cat",
x = "Education",
y = "Readability Score")
# Print the plot
print(p)## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_boxplot()`).## Warning: Removed 664 rows containing missing values or values outside the scale range
## (`geom_point()`).
3 Density Curves
3.1 Density Curves for Academic Status
# Define the function
plot_density_comparison <- function(data, numeric_var_name, group_var_name = "academic_status") {
# Ensure the variable names are non-empty and exist in the dataframe
if (!numeric_var_name %in% names(data)) {
stop("Numeric variable name does not exist in the dataframe.")
}
if (!group_var_name %in% names(data)) {
stop("Group variable name does not exist in the dataframe.")
}
# Use ggplot to create the density plot
p <- ggplot(data, aes_string(x = numeric_var_name, fill = group_var_name)) +
geom_density(alpha = 0.5) + # Adjust alpha for transparency
labs(x = numeric_var_name, y = "Density") + # Labels
ggtitle(paste("Density of", numeric_var_name, "by", group_var_name)) +
scale_fill_manual(values = c("academic" = "skyblue", "non-academic" = "pink")) + # Customize colors
theme_minimal() # Use a minimal theme for a nicer plot
return(p)
}
# Example usage with your dataframe 'data' and the variable 'readability_score'
plot1 <- plot_density_comparison(data, "text_length")## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.# For readability_score
plot2 <- plot_density_comparison(data, "readability_score")
# For leftright_pred_score
plot3 <- plot_density_comparison(data, "leftright_pred_score")
# add type/cluster indicator later
plot1
## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_density()`).
3.2 Density Curves for Education Category
# Define the function
plot_density_comparison <- function(data, numeric_var_name, group_var_name = "educ_cat") {
# Ensure the variable names are non-empty and exist in the dataframe
if (!numeric_var_name %in% names(data)) {
stop("Numeric variable name does not exist in the dataframe.")
}
if (!group_var_name %in% names(data)) {
stop("Group variable name does not exist in the dataframe.")
}
# Use ggplot to create the density plot
p <- ggplot(data, aes_string(x = numeric_var_name, fill = group_var_name)) +
geom_density(alpha = 0.5) + # Adjust alpha for transparency
labs(x = numeric_var_name, y = "Density") + # Labels
ggtitle(paste("Density of", numeric_var_name, "by", group_var_name)) +
scale_fill_manual(values = c("High" = "skyblue", "Intermediate" = "lightgreen", "Low" = "pink")) + # Customize colors
theme_minimal() # Use a minimal theme for a nicer plot
return(p)
}
# Example usage with your dataframe 'data' and the variable 'text_length'
plot5 <- plot_density_comparison(data, "text_length")
# For readability_score
plot6 <- plot_density_comparison(data, "readability_score")
# For leftright_pred_score
plot7 <- plot_density_comparison(data, "leftright_pred_score")
# add type/cluster indicator later
plot5
## Warning: Removed 664 rows containing non-finite outside the scale range
## (`stat_density()`).
3.2.1 Facet Wrap of the Plots
DID NOT WORK YET!!
#library(patchwork)
#
## Assuming plot1, plot2, plot3, plot5, plot6, plot7 are your ggplot objects
#plot_layout <- plot1 + plot2 + plot3 + plot5 + plot6 + plot7 +
# plot_layout(guides = "collect") &
# theme(legend.position = "bottom")
#
#plot_layout <- plot1 + plot2 + plot3 + plot5 + plot6 + plot7 +
# plot_layout(ncol = 2) # This is the correct usage to specify layout options
#
#
#plot_layout